Accurate Image Retrieval Research Articles

Secure and efficient image retrieval based on global features

A few years ago, an image retrieval needs have been increased enormously. Therefore, a need for an efficiency and accurate image retrieval scheme has become desired accordingly. In fact, the images require high storage space; for this reason, cloud computing considers the best selective to outsource images. Many outsourcing images to the cloud server such as medical, police investigation, and personal images that require to encrypt before being outsourced to the cloud servers. However, in this paper a robust scheme has been presented which provides Content Based Image Retrieval (CBIR) over the encrypted images without declassing the important information to the cloud server side. Additionally, the information is exchanging in the strong secure manner among entities. The proposed scheme consists of two phases: setup phase and retrieve phase. The first phase based on build secure dictionary based on global features (intensity of histogram) and images decryption while the second phase utilizes secure query to retrieve the queried image. This scheme is a robust to measure the Euclidean Distance similarity between two queries without decryption. The security and efficiency of the proposed scheme are proofed by security analysis and experiments.

Montage based 3D Medical Image Retrieval from Traumatic Brain Injury Cohort using Deep Convolutional Neural Network.

Brain imaging analysis on clinically acquired computed tomography (CT) is essential for the diagnosis, risk prediction of progression, and treatment of the structural phenotypes of traumatic brain injury (TBI). However, in real clinical imaging scenarios, entire body CT images (e.g., neck, abdomen, chest, pelvis) are typically captured along with whole brain CT scans. For instance, in a typical sample of clinical TBI imaging cohort, only ~15% of CT scans actually contain whole brain CT images suitable for volumetric brain analyses; the remaining are partial brain or non-brain images. Therefore, a manual image retrieval process is typically required to isolate the whole brain CT scans from the entire cohort. However, the manual image retrieval is time and resource consuming and even more difficult for the larger cohorts. To alleviate the manual efforts, in this paper we propose an automated 3D medical image retrieval pipeline, called deep montage-based image retrieval (dMIR), which performs classification on 2D montage images via a deep convolutional neural network. The novelty of the proposed method for image processing is to characterize the medical image retrieval task based on the montage images. In a cohort of 2000 clinically acquired TBI scans, 794 scans were used as training data, 206 scans were used as validation data, and the remaining 1000 scans were used as testing data. The proposed achieved accuracy=1.0, recall=1.0, precision=1.0, f1=1.0 for validation data, while achieved accuracy=0.988, recall=0.962, precision=0.962, f1=0.962 for testing data. Thus, the proposed dMIR is able to perform accurate CT whole brain image retrieval from large-scale clinical cohorts.

Improving Object Retrieval Quality by Integration of Similarity Propagation and Query Expansion

Re-ranking is an essential step for accurate image retrieval, due to its well-known power in performance improvement. Although numerous works have been proposed for re-ranking, many of them are only customized for a certain image representation model. In contrast to most existing techniques, we develop generalized re-ranking algorithms that are applicable to different kinds of image encodings in this paper. We first employ a quite successful theory of similarity propagation to reconstruct vectors of a query and its top ranked images and, subsequently, get a re-ranked list by comparing the new image vectors. Furthermore, considering that the just mentioned strategy is directly compatible with query expansion and, thus, in order to leverage advantages of this milestone, we then propose integrating them into a unified framework for maximizing re-ranking benefits. Our re-ranking algorithms are memory and computation efficient, and experimental results on benchmark datasets demonstrate that they compare favorably with the state of the art. Our code is available at https://github.com/MaJinWakeUp/rerank .

An Unsupervised Multicode Hashing Method for Accurate and Scalable Remote Sensing Image Retrieval

Hashing methods have recently attracted great attention for approximate nearest neighbor search in massive remote sensing (RS) image archives due to their computational and storage effectiveness. The existing hashing methods in RS represent each image with a single-hash code that is usually obtained by applying hash functions to global image representations. Such an approach may not optimally represent the complex information content of RS images. To overcome this problem, in this letter, we present a simple yet effective unsupervised method that represents each image with primitive-cluster sensitive multi-hash codes (each of which corresponds to a primitive present in the image). To this end, the proposed method consists of two main steps: 1) characterization of images by descriptors of primitive-sensitive clusters and 2) definition of multi-hash codes from the descriptors of the primitive-sensitive clusters. After obtaining multi-hash codes for each image, retrieval of images is achieved based on a multi-hash-code-matching scheme. Any hashing method that provides single-hash code can be embedded within the proposed method to provide primitive-sensitive multi-hash codes. Compared with state-of-the-art single-code hashing methods in RS, the proposed method achieves higher retrieval accuracy under the same retrieval time, and thus it is more efficient for operational applications.

Self-feedback image retrieval algorithm based on annular color moments

Content-based image retrieval (CBIR) extracts visual content features (such as color, texture, and shape) of a sample image to retrieve another similar image. Due to the existence of the semantic gap, retrieval results are often unsatisfactory. A CBIR method based on relevance feedback (RF) can reduce the semantic gap and achieve a high-retrieval accuracy by establishing a correlation between low-level image features and high-level semantics via human-computer interaction. However, the complicated human-computer interface of RF increases the burden on users; hence, some scholars have proposed the pseudo-relevance feedback (PRF) technology. To further contribute to the research, this paper proposes a self-feedback image retrieval algorithm based on annular color moments. In this approach, hashing sequences of color moments based on annular segmentation are extracted to be used as feature vectors for initial retrieval. Based on this result, improved subtractive clustering and correlation feedback techniques are used for extended queries. Thus, a self-feedback method without user participation is realized. The experimental results show that the accuracy of image retrieval can be improved, and the proposed algorithm is robust to image rotation, scaling, and translation.

Histopathological Image Retrieval Based on Asymmetric Residual Hash and DNA Coding

Histopathological image retrieval is a key technology for computer-aided diagnosis. However, patients are reluctant to reveal their privacy in histopathological image retrieval. In order to further improve the effectiveness and safety of histopathological image retrieval, this paper proposes a new histopathological retrieval scheme based on asymmetric residual hash (ARH) and DNA coding techniques. In this paper, we first present a novel ARH for histopathological image retrieval to improve the effectiveness of histopathological search scheme, and then we use the 5-D hyperchaotic system to protect patient privacy. Specifically, the contribution consists of four aspects: 1) A histopathology ciphertext domain search scheme was proposed to improve the performance of computer-aided diagnosis. 2) An asymmetric approach was implemented to process histopathological query points and database points, and a novel asymmetric residual hash algorithm was first proposed to improve the accuracy and speed of histopathological image retrieval. 3) The 5-D hyperchaotic system and DNA coding technique are applied to histopathological image retrieval to protect patient privacy. 4) The loss function is constructed and optimized to learn network parameters and hash codes. The simulation experiment was performed on three datasets (Kimia Path24, Kimia Path960, and Malaria), and the results proved the effectiveness of the ARH algorithm. In addition, our proposed search method can resist common types of attacks during histopathological data transmission. Specifically, the MAP of the ARH is 0.9678 on the KIMIA Path24 with the value of hyperparameter is 125 and the length of hash code is 32. The MAP of the ARH is 0.966 on the KIMIA Path960 with the value of hyperparameter is 225 and the length of hash code is 32. The MAP of the ARH is 0.9482 on the Malaria with the value of hyperparameter is 10 and the length of hash code is 24.

A Large-Scale Secure Image Retrieval Method in Cloud Environment

With the rapid development of cloud computing technology, more and more users choose to outsource image data to clouds. To protect data's confidentiality, images need to be encrypted before being outsourced to clouds, but this brings difficulties to some basic yet important data services, such as content-based image retrieval. Existing secure image retrieval methods generally have some problems such as low retrieval accuracy and low retrieval efficiency, which cannot meet requirements for large-scale image retrieval in cloud environment. In this paper, we propose a large-scale secure image retrieval method in cloud environment. The Hamming embedding algorithm is utilized to generate binary signatures of image descriptors. A frequency histogram combined with binary signatures is generated to provide a more precise representation of image features in an image and thus the retrieval accuracy is improved. Visual words are selected from the histogram by the random sampling method before the min-Hash algorithm is performed on binary signatures of selected visual words to generate a secure index. The random sampling method and min-Hash algorithm can not only ensure the security of the search index, but also greatly improve the image retrieval efficiency. This method achieves the balance among security, accuracy and efficiency of large-scale secure image retrieval in public clouds. The security analysis and experimental results show the effectiveness of the proposed method.

Partial-duplicate image retrieval using spatial and visual contextual clues

The traditional bag-of-visual-words (BOW) model quantifies the local features to the visual words to achieve efficient content-based image retrieval. However, since it causes considerable quantisation error and ignores the spatial relationships between visual words, the accuracy of partial-duplicate image retrieval based on BOW model is limited. In order to reduce the quantisation error and improve the discriminability of visual words, many partial-duplicate image retrieval methods have been proposed, which make use of the advantages of the geometric clues between visual words. In this paper, we propose a novel partial-duplicate scheme by using both spatial and visual contextual clues for removing the false matches effectively, which not only encodes the relationships of orientation, distance and dominant orientation between the referential visual word and its context, but also takes the colour information between visual words into consideration. Experimental results reveal that our proposed algorithm achieves superior performance to the state-of-the-art methods for partial-duplicate image retrieval.

Image Retrieval using Visual Phrases

Keypoint based descriptors are widely used for various computer vision applications. During this process, key-points are initially detected from the given images which are later represented by some robust and distinctive descriptors like scale-invariant feature transform (SIFT). Keypoint based image-to-image matching has gained significant accuracy for image retrieval type of applications like image copy detection, similar image retrieval and near duplicate detection. Local keypoint descriptors are quantized into visual words to reduce the feature space which makes image-to-image matching possible for large scale applications. Bag of visual word quantization makes it efficient at the cost of accuracy. In this paper, the bag of visual word model is extended to detect frequent pair of visual words which is known as frequent item-set in text processing, also called visual phrases. Visual phrases increase the accuracy of image retrieval without increasing the vocabulary size. Experiments are carried out on benchmark datasets that depict the effectiveness of proposed scheme.

An Encrypted Image Retrieval Method Based on Harris Corner Optimization and LSH in Cloud Computing

The encrypted image retrieval in cloud computing is a key technology to realize the massive images of storage and management and images safety. In this paper, a novel feature extraction method for encrypted image retrieval is proposed. First, the improved Harris algorithm is used to extract the image features. Next, the Speeded-Up Robust Features algorithm and the Bag of Words model are applied to generate the feature vectors of each image. Then, Local Sensitive Hash algorithm is applied to construct the searchable index for the feature vectors. The chaotic encryption scheme is utilized to protect images and indexes security. Finally, secure similarity search is executed on the cloud server. The experimental results show that compared with the existing encryption retrieval schemes, the proposed retrieval scheme not only reduces the time consumption but also improves the image retrieval accuracy.

Implementation and Comparison of Text-Based Image Retrieval Schemes

Search engines, i.e., Google, Yahoo pro-vide various libraries and API’s to assist programmers and researchers in easier and efficient access to their collected data. When a user generates a search query, the dedicated Application Programming Interface (API) returns the JavaScript Object Notation (JSON) file which contains the desired data. Scraping techniques help image descriptors to separate the image’s URL and web host’s URL in different documents for easier implementation of different algorithms. The aim of this paper is to propose a novel approach to effectively filter out the desired image(s) from the retrieved data. More specifically, this work primarily focuses on applying simple yet efficient techniques to achieve accurate image retrieval. We compare two algorithms, i.e., Cosine similarity and Sequence Matcher, to obtain the accuracy with a minimum of irrelevance. Obtained results prove Cosine similarity more accurate than its counterpart in finding the maximum relevant image(s).

Reversible cellular automata image encryption for similarity search

With the development of cloud computing, people prefer to outsource images to cloud service for saving storage and convenient retrieval. For privacy-preserving purposes, sensitive images, such as medical and personal images, need to be encrypted before outsourcing, which causes the content-based image retrieval technology on plaintext domain unusable. In order to achieve similarity search on encrypted domain, this paper proposes reversible cellular automata image encryption for similarity search. We firstly define the similarity search on encrypted images, and analyze its feasibility when implementing pixel-based deterministic encryption. According to this, we introduce a deterministic encryption based on reversible cellular automata (DERCA). Then we put forward a two-level-granularity image encryption which supports extracting color histogram from encrypted image for similarity search, based on DERCA. The pixels in an image are encrypted in pixel-granularity or pixel-set-granularity to solve utility-security dilemma. And block-based permutation method is used to improve the image security and retrieval accuracy. Experiments on Corel-1000 demonstrate that the proposed method not only offers high image security, but also yields superior retrieval accuracy on encrypted images compared with other image encryption algorithms for similarity search.

Visual attention mechanism and support vector machine based automatic image annotation.

Automatic image annotation not only has the efficiency of text-based image retrieval but also achieves the accuracy of content-based image retrieval. Users of annotated images can locate images they want to search by providing keywords. Currently most automatic image annotation algorithms do not consider the relative importance of each region in the image, and some algorithms extract the image features as a whole. This makes it difficult for annotation words to reflect salient versus non-salient areas of the image. Users searching for images are usually only interested in the salient areas. We propose an algorithm that integrates a visual attention mechanism with image annotation. A preprocessing step divides the image into two parts, the salient regions and everything else, and the annotation step places a greater weight on the salient region. When the image is annotated, words relating to the salient region are given first. The support vector machine uses particle swarm optimization to annotate the images automatically. Experimental results show the effectiveness of the proposed algorithm.

An efficient CBIR system based on color histogram, edge, and texture features

SummaryContent‐based image retrieval (CBIR) has been popular in recent times due to the necessity of storing large database of images in information processing and biomedical applications. However, the accurate retrieval of images and retrieval time are the two major challenges in CBIR systems. Most of the existing works focus on searching the whole database; hence, the retrieval process becomes a time consuming process. This paper proposes an efficient CBIR system, which retrieves images accurately with reasonable retrieval time using the combination of color histogram, edge, and texture features. Initially, the searching is done based on the color similarity and texture using modified Color Difference Histogram (CDH). Then, an edge orientation technique is applied only on the identified images to create a combined feature space. This process greatly reduces the time required for retrieval process due to the absence of fusion process which is quite normal in CBIR systems. Simulations are conducted on the standard databases to show the superior performance of the proposed CBIR system in terms of retrieval time and accuracy.

Attribute Based Image Retrieval and Segmentation using On-tological Approaches

Content based image retrieval is gaining more and more importance as it is an apt approach to retrieve an image. The image is retrieved based on certain texture. Ontology is a branch of Meta Physics that helps in analyzing an input image based on certain textures. Ontology helps to retrieve an image based on its properties. Ontology describes a domain. With that domain, we can proceed further to understand the relation between the features present in the domain. There are biological-ontologies to analyze biological outcomes. The field of information technology can be combined with biological ontology to study the results of different biological effects. With the systematic concept of ontology that includes rules, classes, relations etc we can understand an image better that eventually helps in accurate image retrieval. Ontology can be generic or domain specific. In this paper we will be using domain specific ontology used to analyze the features of digital images along with image segmentation to retrieve an image. We will be testing our proposed system using the colored images of mammals. In case of image segmentation we will using the general techniques already existing.

Speaker Recognition in Content-based Image Retrieval for a High Degree of Accuracy

The purpose of this research is to measure the speaker recognition accuracy in Content-Based Image Retrieval. To support research in speaker recognition accuracy, we use two approaches for recognition system: identification and verification, an identification using fuzzy Mamdani, a verification using Manhattan distance. The test results in this research. The best of distance mean is size 32x32. The best of the verification for distance rate is 965, and the speaker recognition system has a standard error of 5% and the system accuracy is 95%. From these results, we find that there is an increase in accuracy of almost 2.5%. This is due to a combination of two approaches so the system can add to the accuracy of speaker recognition.

Medical Image Retrieval Approach by Texture Features Fusion Based on Hausdorff Distance

Medical images play an important role in the hospital diagnosis and treatment, which include a lot of valuable medical information. Manually annotated viewing is obviously not effective in managing large amounts of medical imaging data. Hence it is an important task to establish an efficient and accurate medical image retrieval system. In this paper, a medical image retrieval approach based on Hausdorff distance combining Tamura texture features and wavelet transform algorithm is proposed. The combination of Tamura texture features and wavelet transform features can extract the texture features of medical images more effectively, and Hausdorff distance can reflect the overall similarity of medical image feature set. In this paper, 6 group experiments of brain MRI database and the lung CT database were conducted separately. Experiments show that the proposed approach has higher accuracy than a single feature texture algorithm and is also higher than the approach of Tamura texture features and wavelet transform features combined with Euclidean distance.

A Semisupervised Framework for Automatic Image Annotation Based on Graph Embedding and Multiview Nonnegative Matrix Factorization

Automatic image annotation is for more accurate image retrieval and classification by assigning labels to images. This paper proposes a semisupervised framework based on graph embedding and multiview nonnegative matrix factorization (GENMF) for automatic image annotation with multilabel images. First, we construct a graph embedding term in the multiview NMF based on the association diagrams between labels for semantic constraints. Then, the multiview features are fused and dimensions are reduced based on multiview NMF algorithm. Finally, image annotation is achieved by using the new features through a KNN-based approach. Experiments validate that the proposed algorithm has achieved competitive performance in terms of accuracy and efficiency.

The Image Retrieval Object Ganesha Image using Invariant Moment Method

In the findings of the statue of Ganesha in Trowulan Mojokerto area is no longer intact, because the statue of Ganesha is found to have been on the surface of soil or underground, so the archaeologist is very difficult to categorize the findings. This research proposes to overcome the above problems it is necessary to the Image Retrieval system (image retrieval) that can provide information about the results of the discovery of such historic objects. For the image taken as Image Retrieval as an example of research trials is the Ganesha Arca. From the Ganesha Statue is searched for feature extraction value by using Moment Invariant method, after which to get the result of image retrieval using Manhattan method. Image Retrieval information system work is image of Ganesa Arca in pre-processing with size 200x260 pixel BMP, then image in edge detection using Roberts method and extraction of Moment Invariant feature and inserted into database as data traning. For data testing the same process with data traning so searched the closest distance using Manhattan method. From the results of 15 image testing statues Ganesha level to the accuracy of the true states there is 62% and stated wrong 38%. Research can be further developed using various methods to improve image retrieval accuracy

Binary Generative Adversarial Networks for Image Retrieval

The most striking successes in image retrieval using deep hashing have mostly involved discriminative models, which require labels. In this paper, we use binary generative adversarial networks (BGAN) to embed images to binary codes in an unsupervised way. By restricting the input noise variable of generative adversarial networks (GAN) to be binary and conditioned on the features of each input image, BGAN can simultaneously learn a binary representation per image, and generate an image plausibly similar to the original one. In the proposed framework, we address two main problems: 1) how to directly generate binary codes without relaxation? 2) how to equip the binary representation with the ability of accurate image retrieval? We resolve these problems by proposing new sign-activation strategy and a loss function steering the learning process, which consists of new models for adversarial loss, a content loss, and a neighborhood structure loss. Experimental results on standard datasets (CIFAR-10, NUSWIDE, and Flickr) demonstrate that our BGAN significantly outperforms existing hashing methods by up to 107% in terms of mAP (See Table 2).